Maintain a per-CPU global "struct pt_regs *" variable which can be used instead
of passing regs around manually through all ~1800 interrupt handlers in the
Linux kernel.
The regs pointer is used in few places, but it potentially costs both stack
space and code to pass it around. On the FRV arch, removing the regs parameter
from all the genirq function results in a 20% speed up of the IRQ exit path
(ie: from leaving timer_interrupt() to leaving do_IRQ()).
Where appropriate, an arch may override the generic storage facility and do
something different with the variable. On FRV, for instance, the address is
maintained in GR28 at all times inside the kernel as part of general exception
handling.
Having looked over the code, it appears that the parameter may be handed down
through up to twenty or so layers of functions. Consider a USB character
device attached to a USB hub, attached to a USB controller that posts its
interrupts through a cascaded auxiliary interrupt controller. A character
device driver may want to pass regs to the sysrq handler through the input
layer which adds another few layers of parameter passing.
I've build this code with allyesconfig for x86_64 and i386. I've runtested the
main part of the code on FRV and i386, though I can't test most of the drivers.
I've also done partial conversion for powerpc and MIPS - these at least compile
with minimal configurations.
This will affect all archs. Mostly the changes should be relatively easy.
Take do_IRQ(), store the regs pointer at the beginning, saving the old one:
struct pt_regs *old_regs = set_irq_regs(regs);
And put the old one back at the end:
set_irq_regs(old_regs);
Don't pass regs through to generic_handle_irq() or __do_IRQ().
In timer_interrupt(), this sort of change will be necessary:
- update_process_times(user_mode(regs));
- profile_tick(CPU_PROFILING, regs);
+ update_process_times(user_mode(get_irq_regs()));
+ profile_tick(CPU_PROFILING);
I'd like to move update_process_times()'s use of get_irq_regs() into itself,
except that i386, alone of the archs, uses something other than user_mode().
Some notes on the interrupt handling in the drivers:
(*) input_dev() is now gone entirely. The regs pointer is no longer stored in
the input_dev struct.
(*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does
something different depending on whether it's been supplied with a regs
pointer or not.
(*) Various IRQ handler function pointers have been moved to type
irq_handler_t.
Signed-Off-By: David Howells <dhowells@redhat.com>
(cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
BUG: warning at kernel/lockdep.c:1816/trace_hardirqs_on() (Not tainted)
Call Trace:
show_trace
dump_stack
trace_hardirqs_on
:forcedeth:nv_nic_irq_other
handle_IRQ_event
__do_IRQ
do_IRQ
ret_from_intr
DWARF2 barf
default_idle
cpu_idle
rest_init
start_kernel
_sinittext
These 3 functions nv_nic_irq_tx(), nv_nic_irq_rx() and nv_nic_irq_other()
are reachable from IRQ context and process context. Make use of the
irq-save/restore spinlock variant.
(Compile tested only, since I do not have the hardware)
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Jeff Garzik <jeff@garzik.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Andrew Morton <akpm@osdl.org>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
There seems to be a possible NULL pointer deref bug in
drivers/net/forcedeth.c::nv_loopback_test(). If dev_alloc_skb() fails, the
next line will call skb_put() with a NULL first argument which it'll then
try to deref - kaboom: a NULL pointer deref. Found by coverity (#1337).
Signed-off-by: Jesper Juhl <jesper.juhl@gmail.com>
Cc: Ayaz Abdulla <aabdulla@nvidia.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: Stephen Hemminger <shemminger@osdl.org>
Cc: Jeff Garzik <jeff@garzik.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
* 'upstream-linus' of master.kernel.org:/pub/scm/linux/kernel/git/jgarzik/netdev-2.6: (217 commits)
net/ieee80211: fix more crypto-related build breakage
[PATCH] Spidernet: add ethtool -S (show statistics)
[NET] GT96100: Delete bitrotting ethernet driver
[PATCH] mv643xx_eth: restrict to 32-bit PPC_MULTIPLATFORM
[PATCH] Cirrus Logic ep93xx ethernet driver
r8169: the MMIO region of the 8167 stands behin BAR#1
e1000, ixgb: Remove pointless wrappers
[PATCH] Remove powerpc specific parts of 3c509 driver
[PATCH] s2io: Switch to pci_get_device
[PATCH] gt96100: move to pci_get_device API
[PATCH] ehea: bugfix for register access functions
[PATCH] e1000 disable device on PCI error
drivers/net/phy/fixed: #if 0 some incomplete code
drivers/net: const-ify ethtool_ops declarations
[PATCH] ethtool: allow const ethtool_ops
[PATCH] sky2: big endian
[PATCH] sky2: fiber support
[PATCH] sky2: tx pause bug fix
drivers/net: Trim trailing whitespace
[PATCH] ehea: IBM eHEA Ethernet Device Driver
...
Manually resolved conflicts in drivers/net/ixgb/ixgb_main.c and
drivers/net/sky2.c related to CHECKSUM_HW/CHECKSUM_PARTIAL changes by
commit 84fa7933a3 that just happened to be
next to unrelated changes in this update.
Replace CHECKSUM_HW by CHECKSUM_PARTIAL (for outgoing packets, whose
checksum still needs to be completed) and CHECKSUM_COMPLETE (for
incoming packets, device supplied full checksum).
Patch originally from Herbert Xu, updated by myself for 2.6.18-rc3.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
This removes unnecessary messages that show up every time I put my
ethernet card in promiscuous mode. I'm already getting notification
from the networking layer, I don't need notification from the driver as
well.
There are probably other drivers that do this as well -- I'll look
around and see what I can find.
Signed-off-by: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch decouples the dependency between the rx checksum feature and
vlan feature. This is done by ignoring the checksum information if the
user has disabled rx checksum when vlan is enabled.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch addresses an errata found on certain marvell phys concerning
the reset of the BMCR phy register during phy reset.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
From: Michal Piotrowski <michal.k.k.piotrowski@gmail.com>
Signed-off-by: Michal Piotrowski <michal.k.k.piotrowski@gmail.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Revised version of the forcedeth NAPI support.
This version is based against netdev-2.6#upstream
(after the MAC patches from Ayaz today).
Can't use nv_disable_hw_interrupts because NAPI only wants to
mask off receive irq's and leave the others alone.
Signed-off-by: Stephen Hemminger <shemminger@osdl.org>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch will correct the mac address and set a flag to indicate that
it is already corrected in case nv_probe is called again. For example,
when you use kexec to restart the kernel.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch moves the mac address setup/teardown to the
nv_probe/nv_remove functions. This fixes WOL wakeup since on nv_close we
would reverse the mac address. Also, bonding driver will reset address
after nv_close is called.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Use __le32 to indicate byte order of hardware ring elements
Signed-off-by: Stephen Hemminger <shemminger@osdl.org>
drivers/net/forcedeth.c | 16 ++++++++--------
1 file changed, 8 insertions(+), 8 deletions(-)
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Fix the coding style of the nForce Ethernet driver.
- typedef's should not be used
- variable names should not be capitialized
- structure tags should be lower case
- add whitespace near keywords
- don't add paren's to switch cases
- remove paren's from return
- don't use __constant_ntohs unless necessary.
Signed-off-by: Stephen Hemminger <shemminger@osdl.org>
drivers/net/forcedeth.c | 246 ++++++++++++++++++++++++------------------------
1 file changed, 123 insertions(+), 123 deletions(-)
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch defines the watermark registers and fixes up the use of this
register.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch adds the definition for the deferral registers and fixes up
the use of these registers.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch adds the wrapper function skb_is_gso which can be used instead
of directly testing skb_shinfo(skb)->gso_size. This makes things a little
nicer and allows us to change the primary key for indicating whether an skb
is GSO (if we ever want to do that).
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
nv_do_nic_poll() is called from timer softirqs, which has interrupts enabled,
but np->lock might also be taken by some other interrupt context.
The driver does disable_irq() to get around this problem, so annotate the
disable_irq()/enable_irq() calls for lockdep.
Has no effect on non-lockdep kernels.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Ayaz Abdulla <aabdulla@nvidia.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: Jeff Garzik <jeff@garzik.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Someone went nuts in there.
Cc: Ayaz Abdulla <aabdulla@nvidia.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: Jeff Garzik <jeff@garzik.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Having separate fields in sk_buff for TSO/UFO (tso_size/ufo_size) is not
going to scale if we add any more segmentation methods (e.g., DCCP). So
let's merge them.
They were used to tell the protocol of a packet. This function has been
subsumed by the new gso_type field. This is essentially a set of netdev
feature bits (shifted by 16 bits) that are required to process a specific
skb. As such it's easy to tell whether a given device can process a GSO
skb: you just have to and the gso_type field and the netdev's features
field.
I've made gso_type a conjunction. The idea is that you have a base type
(e.g., SKB_GSO_TCPV4) that can be modified further to support new features.
For example, if we add a hardware TSO type that supports ECN, they would
declare NETIF_F_TSO | NETIF_F_TSO_ECN. All TSO packets with CWR set would
have a gso_type of SKB_GSO_TCPV4 | SKB_GSO_TCPV4_ECN while all other TSO
packets would be SKB_GSO_TCPV4. This means that only the CWR packets need
to be emulated in software.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch makes the needlessly global nv_update_pause() static.
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
There has been an update to the forcedeth driver that added a few new
uses of xmit_lock which is no longer meant to be used directly. This
patch replaces them with netif_tx_lock_bh.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6: (109 commits)
[ETHTOOL]: Fix UFO typo
[SCTP]: Fix persistent slowdown in sctp when a gap ack consumes rx buffer.
[SCTP]: Send only 1 window update SACK per message.
[SCTP]: Don't do CRC32C checksum over loopback.
[SCTP] Reset rtt_in_progress for the chunk when processing its sack.
[SCTP]: Reject sctp packets with broadcast addresses.
[SCTP]: Limit association max_retrans setting in setsockopt.
[PFKEYV2]: Fix inconsistent typing in struct sadb_x_kmprivate.
[IPV6]: Sum real space for RTAs.
[IRDA]: Use put_unaligned() in irlmp_do_discovery().
[BRIDGE]: Add support for NETIF_F_HW_CSUM devices
[NET]: Add NETIF_F_GEN_CSUM and NETIF_F_ALL_CSUM
[TG3]: Convert to non-LLTX
[TG3]: Remove unnecessary tx_lock
[TCP]: Add tcp_slow_start_after_idle sysctl.
[BNX2]: Update version and reldate
[BNX2]: Use CPU native page size
[BNX2]: Use compressed firmware
[BNX2]: Add firmware decompression
[BNX2]: Allow WoL settings on new 5708 chips
...
Manual fixup for conflict in drivers/net/tulip/winbond-840.c
Various drivers use xmit_lock internally to synchronise with their
transmission routines. They do so without setting xmit_lock_owner.
This is fine as long as netpoll is not in use.
With netpoll it is possible for deadlocks to occur if xmit_lock_owner
isn't set. This is because if a printk occurs while xmit_lock is held
and xmit_lock_owner is not set can cause netpoll to attempt to take
xmit_lock recursively.
While it is possible to resolve this by getting netpoll to use
trylock, it is suboptimal because netpoll's sole objective is to
maximise the chance of getting the printk out on the wire. So
delaying or dropping the message is to be avoided as much as possible.
So the only alternative is to always set xmit_lock_owner. The
following patch does this by introducing the netif_tx_lock family of
functions that take care of setting/unsetting xmit_lock_owner.
I renamed xmit_lock to _xmit_lock to indicate that it should not be
used directly. I didn't provide irq versions of the netif_tx_lock
functions since xmit_lock is meant to be a BH-disabling lock.
This is pretty much a straight text substitution except for a small
bug fix in winbond. It currently uses
netif_stop_queue/spin_unlock_wait to stop transmission. This is
unsafe as an IRQ can potentially wake up the queue. So it is safer to
use netif_tx_disable.
The hamradio bits used spin_lock_irq but it is unnecessary as
xmit_lock must never be taken in an IRQ handler.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch contains new device ids for forcedeth ethernet.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch bumps up the version number for config support.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch adds support for diagnostic tests through ethtool support.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch moves a few functions (no logic change) so that the next
patch has these functions defined.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch exposes hardware statistic counters through ethtool support.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch allows for configurable rx and tx checksum offloads through
ethtool support.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch fixes configuration bugs when modifying wol settings.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch fixes configuration bugs when modifying phy settings.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch allows for configurable flow control through ethtool support.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch allows for configurable ring size through ethtool support.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
There are a series of patches for configuration support in forcedeth and
one patch for device ids.
This patch is a cleanup of the a previous TSO patch.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch adds flow control support for tx and rx pause frames in
forcedeth.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
With Manfred Spraul <manfred@colorfullife.com> and
Andrew Morton <akpm@osdl.org>
Bring back this recently-reverted patch, only fixed.
Original changelog:
From: Ayaz Abdulla <aabdulla@nvidia.com>
This patch fixes the issues with multiple irqs.
I am resending based on feedback. I decoupled the dma mask for
consistent memory and fixed leak with multiple irq in error path.
Thanks to Manfred for catching the spin lock problem.
Fix it:
From: Manfred Spraul <manfred@colorfullife.com>
Fix bug introduced by ebf34c9b6f, covered in
http://bugzilla.kernel.org/show_bug.cgi?id=6568.
Remove second instance of the request_irq() calls: they were moved
from nv_open into nv_request_irq.
Thanks to Alistair Strachan <alistair@devzero.co.uk> for reporting and
persisting.
Signed-off-by: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Manfred Spraul <manfred@colorfullife.com>
Cc: Jeff Garzik <jeff@garzik.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Revert ebf34c9b6f. Maybe. Due to crashes
at shutdown - see http://bugzilla.kernel.org/show_bug.cgi?id=6568.
Cc: Ayaz Abdulla <aabdulla@nvidia.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: Jeff Garzik <jeff@garzik.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch fixes the issues with multiple irqs.
I am resending based on feedback. I decoupled the dma mask for
consistent memory and fixed leak with multiple irq in error path.
Thanks to Manfred for catching the spin lock problem.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
This patch fixes the nic initialization. If the nic was in low power
mode, it brings it back to normal power. Also, it utilizes a new
hardware reset during the init.
I am resending based on feedback, I corrected the register size mapping
and delay after posted write.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Replace all occurences of 0xff.. in calls to function pci_set_dma_mask()
and pci_set_consistant_dma_mask() with the corresponding DMA_xBIT_MASK from
linux/dma-mapping.h.
Signed-off-by: Matthias Gehre <M.Gehre@gmx.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This forcedeth patch adds support for MSI/MSIX interrupts.
Signed-off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jgarzik@pobox.com>
This forcedeth patch adds high dma support for tx/rx rings.
Signed-off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jgarzik@pobox.com>
This forcedeth patch adds support for vlan stripping/inserting in hardware.
Signed-off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jgarzik@pobox.com>
This contains a bug fix for large buffers. Originally, if a tx buffer to
be sent was larger then the maximum size of the tx descriptor, it would
overwrite other control bits. In this patch, the buffer is split over
multiple descriptors. Also, the fragments are now setup in forward order.
Signed-off-by: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Jeff Garzik <jgarzik@pobox.com>
Two critical bugs were found in forcedeth 0.47:
- TSO doesn't work.
- pci_map_single() for the rx buffers is called with size==0. This bug
is critical, it causes random memory corruptions on systems with an
iommu.
Below is a minimal fix for both bugs, for 2.6.15.
TSO will be fixed properly in the next version. Tested on x86-64.
Signed-Off-By: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch contains support for different modes of interrupt mitigation
of forcedeth. It includes changes based on Jeff's comments. Currently,
the modes are changed through module parameters since ethtool does not
support something similar.
Signed-off-by: Ayaz Abdulla <aabdulla@nvidia.com>
Recent forcedeth nics support checksum offloading for tx.
The attached patch, written by Ayaz Abdulla, adds the support to the
driver.
It also cleans up the handling of the three dma ring entry formats that
are supported by the driver.
Signed-off-By: Manfred Spraul <manfred@colorfullife.com>
Signed-off-By: Jeff Garzik <jgarzik@pobox.com>
Add support for ETHTOOL_GPERMADDR to forcedeth.
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Jeff Garzik <jgarzik@pobox.com>
Rüdiger found a bug in nv_open that explains some of the reports
with duplex mismatches:
nv_open calls nv_update_link_speed for initializing the hardware link speed
registers. If current link setting matches the values in np->linkspeed and
np->duplex, then the function does nothing.
Usually, doing nothing is the right thing, but not in nv_open: During
nv_open, the registers must be initialized because the nic was reset.
The attached patch fixes that by setting np->linkspeed to an invalid value
before calling nv_update_link_speed from nv_open.
Signed-Off-By: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Jeff Garzik <jgarzik@pobox.com>
Ayaz wrote an update to the error handling for forcedeth (which I
modified heavily, thus all bugs are mine):
The ERROR4 bit is not a fatal error, it just indicates a mismatch
between the actual packet len and the len according to the 802.3 header.
The patch adds proper handling.
The patch also removes the code that drops all packets with RX_ERROR &
(!RX_FRAMINGERR): ERROR4 errors are also not fatal.
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
Jeff Garzik